from google.colab import drive
import datetime
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
drive.mount('/content/drive')

Mounted at /content/drive

df = pd.read_csv("/content/drive/My Drive/data/hotel_bookings.csv")

df_notcanceled = df[(df['is_canceled'] == 0)]
df_canceled = df[(df['is_canceled'] == 1)]

columns = ['lead_time', 'stays_in_weekend_nights', 'stays_in_week_nights', 'adults', 'children', 'babies', 'required_car_parking_spaces', 'adr', 'previous_cancellations', 'previous_bookings_not_canceled', 'booking_changes']
n = 1
plt.figure(figsize=(40,30))

for column in list(df):
  plt.subplot(6,5,n)
  n = n+1  
  sns.countplot(x=column, data=df,hue = 'is_canceled',order=pd.value_counts(df[column]).iloc[:13].index)
    
  plt.tight_layout()

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 119390 entries, 0 to 119389
Data columns (total 32 columns):
 #   Column                          Non-Null Count   Dtype  
---  ------                          --------------   -----  
 0   hotel                           119390 non-null  object 
 1   is_canceled                     119390 non-null  int64  
 2   lead_time                       119390 non-null  int64  
 3   arrival_date_year               119390 non-null  int64  
 4   arrival_date_month              119390 non-null  object 
 5   arrival_date_week_number        119390 non-null  int64  
 6   arrival_date_day_of_month       119390 non-null  int64  
 7   stays_in_weekend_nights         119390 non-null  int64  
 8   stays_in_week_nights            119390 non-null  int64  
 9   adults                          119390 non-null  int64  
 10  children                        119386 non-null  float64
 11  babies                          119390 non-null  int64  
 12  meal                            119390 non-null  object 
 13  country                         118902 non-null  object 
 14  market_segment                  119390 non-null  object 
 15  distribution_channel            119390 non-null  object 
 16  is_repeated_guest               119390 non-null  int64  
 17  previous_cancellations          119390 non-null  int64  
 18  previous_bookings_not_canceled  119390 non-null  int64  
 19  reserved_room_type              119390 non-null  object 
 20  assigned_room_type              119390 non-null  object 
 21  booking_changes                 119390 non-null  int64  
 22  deposit_type                    119390 non-null  object 
 23  agent                           103050 non-null  float64
 24  company                         6797 non-null    float64
 25  days_in_waiting_list            119390 non-null  int64  
 26  customer_type                   119390 non-null  object 
 27  adr                             119390 non-null  float64
 28  required_car_parking_spaces     119390 non-null  int64  
 29  total_of_special_requests       119390 non-null  int64  
 30  reservation_status              119390 non-null  object 
 31  reservation_status_date         119390 non-null  object 
dtypes: float64(4), int64(16), object(12)
memory usage: 29.1+ MB

df[df.isnull().any(axis=1)]

	hotel	is_canceled	lead_time	arrival_date_year	arrival_date_month	arrival_date_week_number	arrival_date_day_of_month	stays_in_weekend_nights	stays_in_week_nights	adults	children	babies	meal	country	market_segment	distribution_channel	is_repeated_guest	previous_cancellations	previous_bookings_not_canceled	reserved_room_type	assigned_room_type	booking_changes	deposit_type	agent	company	days_in_waiting_list	customer_type	adr	required_car_parking_spaces	total_of_special_requests	reservation_status	reservation_status_date
0	Resort Hotel	0	342	2015	July	27	1	0	0	2	0.0	0	BB	PRT	Direct	Direct	0	0	0	C	C	3	No Deposit	NaN	NaN	0	Transient	0.00	0	0	Check-Out	2015-07-01
1	Resort Hotel	0	737	2015	July	27	1	0	0	2	0.0	0	BB	PRT	Direct	Direct	0	0	0	C	C	4	No Deposit	NaN	NaN	0	Transient	0.00	0	0	Check-Out	2015-07-01
2	Resort Hotel	0	7	2015	July	27	1	0	1	1	0.0	0	BB	GBR	Direct	Direct	0	0	0	A	C	0	No Deposit	NaN	NaN	0	Transient	75.00	0	0	Check-Out	2015-07-02
3	Resort Hotel	0	13	2015	July	27	1	0	1	1	0.0	0	BB	GBR	Corporate	Corporate	0	0	0	A	A	0	No Deposit	304.0	NaN	0	Transient	75.00	0	0	Check-Out	2015-07-02
4	Resort Hotel	0	14	2015	July	27	1	0	2	2	0.0	0	BB	GBR	Online TA	TA/TO	0	0	0	A	A	0	No Deposit	240.0	NaN	0	Transient	98.00	0	1	Check-Out	2015-07-03
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
119385	City Hotel	0	23	2017	August	35	30	2	5	2	0.0	0	BB	BEL	Offline TA/TO	TA/TO	0	0	0	A	A	0	No Deposit	394.0	NaN	0	Transient	96.14	0	0	Check-Out	2017-09-06
119386	City Hotel	0	102	2017	August	35	31	2	5	3	0.0	0	BB	FRA	Online TA	TA/TO	0	0	0	E	E	0	No Deposit	9.0	NaN	0	Transient	225.43	0	2	Check-Out	2017-09-07
119387	City Hotel	0	34	2017	August	35	31	2	5	2	0.0	0	BB	DEU	Online TA	TA/TO	0	0	0	D	D	0	No Deposit	9.0	NaN	0	Transient	157.71	0	4	Check-Out	2017-09-07
119388	City Hotel	0	109	2017	August	35	31	2	5	2	0.0	0	BB	GBR	Online TA	TA/TO	0	0	0	A	A	0	No Deposit	89.0	NaN	0	Transient	104.40	0	0	Check-Out	2017-09-07
119389	City Hotel	0	205	2017	August	35	29	2	7	2	0.0	0	HB	DEU	Online TA	TA/TO	0	0	0	A	A	0	No Deposit	9.0	NaN	0	Transient	151.20	0	2	Check-Out	2017-09-07

119173 rows × 32 columns

df.isnull().sum()

hotel                                  0
is_canceled                            0
lead_time                              0
arrival_date_year                      0
arrival_date_month                     0
arrival_date_week_number               0
arrival_date_day_of_month              0
stays_in_weekend_nights                0
stays_in_week_nights                   0
adults                                 0
children                               4
babies                                 0
meal                                   0
country                              488
market_segment                         0
distribution_channel                   0
is_repeated_guest                      0
previous_cancellations                 0
previous_bookings_not_canceled         0
reserved_room_type                     0
assigned_room_type                     0
booking_changes                        0
deposit_type                           0
agent                              16340
company                           112593
days_in_waiting_list                   0
customer_type                          0
adr                                    0
required_car_parking_spaces            0
total_of_special_requests              0
reservation_status                     0
reservation_status_date                0
dtype: int64

df = df.drop(['agent','company'],axis= 1).dropna()

removed distribution channel becuase its same as market segment and agent and company have so large number of missing values

df.isnull().sum()

hotel                             0
is_canceled                       0
lead_time                         0
arrival_date_year                 0
arrival_date_month                0
arrival_date_week_number          0
arrival_date_day_of_month         0
stays_in_weekend_nights           0
stays_in_week_nights              0
adults                            0
children                          0
babies                            0
meal                              0
country                           0
market_segment                    0
is_repeated_guest                 0
previous_cancellations            0
previous_bookings_not_canceled    0
reserved_room_type                0
assigned_room_type                0
booking_changes                   0
deposit_type                      0
days_in_waiting_list              0
customer_type                     0
adr                               0
required_car_parking_spaces       0
total_of_special_requests         0
reservation_status                0
reservation_status_date           0
dtype: int64

n = df.nunique(axis=0)
  
print("No.of.unique values in each column :\n",
      n)

No.of.unique values in each column :
 hotel                                2
is_canceled                          2
lead_time                          479
arrival_date_year                    3
arrival_date_month                  12
arrival_date_week_number            53
arrival_date_day_of_month           31
stays_in_weekend_nights             15
stays_in_week_nights                33
adults                              14
children                             5
babies                               5
meal                                 5
country                            177
market_segment                       7
is_repeated_guest                    2
previous_cancellations              15
previous_bookings_not_canceled      73
reserved_room_type                  10
assigned_room_type                  12
booking_changes                     21
deposit_type                         3
days_in_waiting_list               128
customer_type                        4
adr                               8870
required_car_parking_spaces          5
total_of_special_requests            6
reservation_status                   3
reservation_status_date            926
dtype: int64

df.head()

	hotel	is_canceled	lead_time	arrival_date_year	arrival_date_month	arrival_date_week_number	arrival_date_day_of_month	stays_in_weekend_nights	stays_in_week_nights	adults	children	babies	meal	country	market_segment	distribution_channel	is_repeated_guest	previous_cancellations	previous_bookings_not_canceled	reserved_room_type	assigned_room_type	booking_changes	deposit_type	days_in_waiting_list	customer_type	adr	required_car_parking_spaces	total_of_special_requests	reservation_status	reservation_status_date
0	Resort Hotel	0	342	2015	July	27	1	0	0	2	0.0	0	BB	PRT	Direct	Direct	0	0	0	C	C	3	No Deposit	0	Transient	0.0	0	0	Check-Out	2015-07-01
1	Resort Hotel	0	737	2015	July	27	1	0	0	2	0.0	0	BB	PRT	Direct	Direct	0	0	0	C	C	4	No Deposit	0	Transient	0.0	0	0	Check-Out	2015-07-01
2	Resort Hotel	0	7	2015	July	27	1	0	1	1	0.0	0	BB	GBR	Direct	Direct	0	0	0	A	C	0	No Deposit	0	Transient	75.0	0	0	Check-Out	2015-07-02
3	Resort Hotel	0	13	2015	July	27	1	0	1	1	0.0	0	BB	GBR	Corporate	Corporate	0	0	0	A	A	0	No Deposit	0	Transient	75.0	0	0	Check-Out	2015-07-02
4	Resort Hotel	0	14	2015	July	27	1	0	2	2	0.0	0	BB	GBR	Online TA	TA/TO	0	0	0	A	A	0	No Deposit	0	Transient	98.0	0	1	Check-Out	2015-07-03

sns.countplot(x='country', data=df,order=pd.value_counts(df['country']).iloc[:10].index,palette= 'colorblind')
plt.title('Top 10 Countries of Origin of the Guests', weight='bold')
plt.xlabel('Country')
plt.ylabel('Reservation Count')

Text(0, 0.5, 'Reservation Count')

df['country'].value_counts(normalize = True)[:10]

PRT    0.408636
GBR    0.102012
FRA    0.087596
ESP    0.072062
DEU    0.061288
ITA    0.031674
IRL    0.028386
BEL    0.019698
BRA    0.018705
NLD    0.017696
Name: country, dtype: float64

sns.barplot(x = "country", y = "is_canceled",order=pd.value_counts(df['country']).iloc[:10].index, hue="hotel",hue_order = ["City Hotel", "Resort Hotel"],data=df,palette= 'Blues')
plt.title("cancelation on basis of country", weight = 'bold')
plt.xlabel("country")
plt.ylabel("Cancelations %")
plt.legend(loc="upper right")
plt.show()

cancelation of city hotel are more from every coutry tourist than resort hotel so we can conclude that confirmed booking and check in percentage is more for resort hotel

NLD has lesser percentage of cancelations of resort hotel so chances of NLD booking confirmed for resort hotel is more

and DEU has lesser percentage of cancelations of city hotel so chances of DEU booking confirmed for city hotel is more

sns.barplot(x = "market_segment", y = "is_canceled",order=pd.value_counts(df['market_segment']).iloc[:10].index, hue="hotel",hue_order = ["City Hotel", "Resort Hotel"],data=df,palette= 'Set1')
plt.title("cancelation on basis of marketsegment", weight = 'bold')
plt.xlabel("market_segment")

plt.ylabel("Cancelations %")
plt.legend(loc="upper right")
plt.show()

sns.countplot(x = "arrival_date_month",order=pd.value_counts(df_notcanceled['arrival_date_month']).iloc[:10].index, hue="hotel",hue_order = ["City Hotel", "Resort Hotel"],data=df_notcanceled,palette= 'Set1')
plt.title("cancelation on basis of arrival_date_month", weight = 'bold')
plt.xlabel("arrival_date_month")

plt.ylabel("count")
plt.legend(loc="upper right")
plt.show()

sns.countplot(x = "arrival_date_month",order=pd.value_counts(df_canceled['arrival_date_month']).iloc[:10].index, hue="hotel",hue_order = ["City Hotel", "Resort Hotel"],data=df_canceled,palette= 'Set1')
plt.title("cancelation on basis of arrival_date_month", weight = 'bold')
plt.xlabel("arrival_date_month")

plt.ylabel("count")
plt.legend(loc="upper right")
plt.show()

as we can see groups cancels more than other market segments

no cancelation of resort hotel from aviation

lowest cancelataion of city hotel from complementary marget segment(only case where cancelation of city hotel is lesser than resort hotel)

lesser number of cancelations are from direct

so chances of direct market segment booking confirmed is more

sns.countplot(df['market_segment'],order=pd.value_counts(df['market_segment']).index)
plt.title('Total Number of Bookings by market_segment',weight = 'bold')
plt.xticks(rotation=45)
plt.xlabel('Market Segment')
plt.ylabel('Reservation Count')

/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning

Text(0, 0.5, 'Reservation Count')

56402

sns.barplot(x = "market_segment", y = "is_canceled",order=pd.value_counts(df['market_segment']).iloc[:10].index, hue="is_repeated_guest",hue_order = [0, 1],data=df,palette= 'Set2')
plt.title("cancelation on basis of marketsegment on basis of repeated guest", weight = 'bold')
plt.xlabel("market_segment")
plt.xticks(rotation=45)
plt.ylabel("Cancelations %")
plt.legend(loc="upper right")
plt.show()

we can conclude that repeated guest do less cancelations excluding the groups

corporate repeated guest from NLD for resort hotel have maximum chances for confirm check in

onlineTA prefer to be a repeated guest more

sns.countplot(df['customer_type'],order=pd.value_counts(df['customer_type']).index)
plt.title('Total Number of Bookings by Customer Type',weight = 'bold')
plt.xlabel('Market Segment')
plt.ylabel('Reservation Count')

/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning

Text(0, 0.5, 'Reservation Count')

#plt.figure(figsize=(7,4))
sns.barplot(x = "deposit_type", y = "is_canceled",order=pd.value_counts(df['deposit_type']).iloc[:10].index, hue="customer_type",data=df,palette= 'Set3')
plt.title("cancelation on basis of marketsegment on basis of customer_type", weight = 'bold')
plt.xlabel("deposit_type")
plt.ylabel("Cancelations %")
plt.legend(loc="upper left")
plt.show()

refundable and non refundable group cancelations are negligible

but non refund deposit type excluding groups are so high

fig = plt.figure(figsize = (15,20))
ax = fig.gca()
df.hist(ax = ax)

/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:3: UserWarning: To output multiple subplots, the figure containing the passed axes is being cleared
  This is separate from the ipykernel package so we can avoid doing imports until

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7f424a5af3d0>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424afb5310>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424af61350>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424a9626d0>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x7f424a8c38d0>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424aeff990>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f4259e82fd0>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424ac77c90>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x7f424ac77550>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424b166d10>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f4259e53a50>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424a681e90>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x7f424ac27550>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424a94bb90>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424b057290>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424adba990>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x7f424b03cf50>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424a705610>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424b1fac90>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f424a76a490>]],
      dtype=object)

sns.pairplot(df,hue="is_canceled",height=3)

/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:306: UserWarning: Dataset has 0 variance; skipping density estimate.
  warnings.warn(msg, UserWarning)

<seaborn.axisgrid.PairGrid at 0x7f42419ec3d0>

columns = ['lead_time', 'stays_in_weekend_nights', 'stays_in_week_nights', 'adults', 'children', 'babies', 'required_car_parking_spaces', 'adr', 'previous_cancellations', 'previous_bookings_not_canceled', 'booking_changes']
n = 1
plt.figure(figsize=(20,15))

for column in columns:
  plt.subplot(4,4,n)
  n = n+1
  sns.boxplot(df[column])
  plt.tight_layout()

/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning

boxplot to check outliner

for column in columns:
  print(column,"0.35% quantile",df[column].quantile(0.0035))
  print(column,"99.65% quantile",df[column].quantile(0.9965))
  df[column] = np.where(df[column] <df[column].quantile(0.0035), df[column].quantile(0.0035),df[column])
  df[column] = np.where(df[column] >df[column].quantile(0.9965), df[column].quantile(0.9965),df[column])
  print(df[column].skew())

lead_time 0.35% quantile 0.0
lead_time 99.65% quantile 510.0
1.2740614632943779
stays_in_weekend_nights 0.35% quantile 0.0
stays_in_weekend_nights 99.65% quantile 4.0
0.7337756720816102
stays_in_week_nights 0.35% quantile 0.0
stays_in_week_nights 99.65% quantile 10.0
1.442579439937437
adults 0.35% quantile 1.0
adults 99.65% quantile 3.0
-0.39041531267706353
children 0.35% quantile 0.0
children 99.65% quantile 2.0
3.9504928514300564
babies 0.35% quantile 0.0
babies 99.65% quantile 1.0
11.273699163521435
required_car_parking_spaces 0.35% quantile 0.0
required_car_parking_spaces 99.65% quantile 1.0
3.6511589224755103
adr 0.35% quantile 0.0
adr 99.65% quantile 289.0
0.9201647682817626
previous_cancellations 0.35% quantile 0.0
previous_cancellations 99.65% quantile 2.0
4.475412768953266
previous_bookings_not_canceled 0.35% quantile 0.0
previous_bookings_not_canceled 99.65% quantile 9.0
9.971737517970483
booking_changes 0.35% quantile 0.0
booking_changes 99.65% quantile 4.0
3.3958641878172173

outliners removed taking 0.35 percentile as lower z score and 99.65 as higher z score

n = 1
plt.figure(figsize=(20,15))

for column in columns:
  plt.subplot(4,4,n)
  n = n+1
  sns.boxplot(df[column])
  plt.tight_layout()

/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning

ordered_months = ["January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December"]
df['arrival_date_month'] = pd.Categorical(df['arrival_date_month'], categories=ordered_months, ordered=True)
plt.figure(figsize=(12,6))
sns.lineplot(x='arrival_date_month', y="adr" ,hue='hotel', data= df)
plt.show()

df_not_canceled = df[df['is_canceled'] == 0]

x,y = get_count(df_not_canceled['arrival_date_year'])

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-33-4fbef0008efd> in <module>()
----> 1 x,y = get_count(df_not_canceled['arrival_date_year'])

NameError: name 'get_count' is not defined

df['arrival_date_year'] = df['arrival_date_year'].apply(str)
plt.figure(figsize=(12,6))
sns.lineplot(x='arrival_date_year', y= ,hue='hotel', data= df)
plt.show()

plt.figure(figsize=(12,6))
sns.lineplot(x = "arrival_date_month", y = "adr", hue="is_canceled",hue_order= [1,0],data=df,palette= 'Set1')
plt.title("Relationship between ADR and Arrival Month by Booking cancellation status", weight = 'bold')
plt.xlabel("Arrival Month")
plt.xticks(rotation=45)
plt.ylabel("Average Daily Rate")
plt.legend(loc="upper right")
plt.show()

we can conclude that adr is on peak in august month ie busiest month

fig, ax = plt.subplots(figsize=(22,15))
sns.heatmap(df.corr(), annot=True, ax=ax);

lead time has most impact on cancelations as lead time increasing chances of cancelation increase

and in case of special requests the more of special request the lesser are chances of cancelation

city hotel is most booked and canceled but rate of cancelation is less in resort hotel that means those who book resort hotel are maximum sure that they dont need to cancel

as a conclusion on analysing everything that most of the guests prefer to visit in summer as we can see (mostly busiest months are may july august)

atleast one parking space required for every guest

maintain the rooms according to family with babies or childrens(mostly visited by 2 guest with no babies or childrens) so to increase room space maybe helpful

repeated guests are more maybe on asking them what make them to visit here again and again can helpful

adr 65 having good results cant consider 0 because its free

mostly guest stayed for upto 2 nights prefering BB that means morning arrival are more

most guest prefer no deposit that means pay on arrival

as we can see from heatmap that repeated guest and previous booking not cancelled is correlated as the number of adult and childrens increase with guest adr increase and most of the special request are of car parking space